© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3715
    Prev
    Next
    INDEX
    Explanations

    formatted text and coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.68
     BoxDecoration
    -0.64
    CppMethod
    -0.64
    '});
    -0.63
     ContentValues
    -0.61
    setVerticalGroup
    -0.59
    setViewportView
    -0.58
    +#+#
    -0.58
     pinulongan
    -0.58
    AddTagHelper
    -0.58
    POSITIVE LOGITS
    <strong>
    2.67
    <em>
    1.16
    </strong>
    1.05
    </em>
    0.81
    <code>
    0.80
    <u>
    0.78
    <sub>
    0.64
    <h1>
    0.57
    <h4>
    0.56
    <i>
    0.56
    Activations Density 0.037%

    No Known Activations